Merge pull request #4163 from santiagxf/santiagxf-patch-1

Image embeddings fix

Author: prmerger-automator[bot]

articles/ai-foundry/model-inference/includes/use-image-embeddings/csharp.md

@@ -36,7 +36,7 @@ First, create the client to consume the model. The following code uses an endpoi
 
 
 ```csharp
-EmbeddingsClient client = new EmbeddingsClient(
+ImageEmbeddingsClient client = new ImageEmbeddingsClient(
     new Uri("https://<resource>.services.ai.azure.com/models"),
     new AzureKeyCredential(Environment.GetEnvironmentVariable("AZURE_INFERENCE_CREDENTIAL"))
 );
@@ -51,7 +51,7 @@ BearerTokenAuthenticationPolicy tokenPolicy = new BearerTokenAuthenticationPolic
 
 clientOptions.AddPolicy(tokenPolicy, HttpPipelinePosition.PerRetry);
 
-client = new EmbeddingsClient(
+ImageEmbeddingsClient client = new ImageEmbeddingsClient(
     new Uri("https://<resource>.services.ai.azure.com/models"),
     credential,
     clientOptions

articles/ai-foundry/model-inference/includes/use-image-embeddings/javascript.md

@@ -99,7 +99,7 @@ var image_path = "sample1.png";
 var image_data = fs.readFileSync(image_path);
 var image_data_base64 = Buffer.from(image_data).toString("base64");
 
-var response = await client.path("images/embeddings").post({
+var response = await client.path("/images/embeddings").post({
     body: {
         input: [
             {
@@ -120,7 +120,7 @@ The following example shows how to create embeddings that are used to create an
 
 
 ```javascript
-var response = await client.path("/embeddings").post({
+var response = await client.path("/images/embeddings").post({
     body: {
         input: [ { image: image_data_base64 } ],
         input_type: "document",
@@ -133,7 +133,7 @@ When you work on a query to retrieve such a document, you can use the following
 
 
 ```javascript
-var response = await client.path("/embeddings").post({
+var response = await client.path("/images/embeddings").post({
     body: {
         input: [ { image: image_data_base64 } ],
         input_type: "query",